Forward Deployed Engineer - India

Forward Deployed Engineer · Mid · Full Time · Remote

India · RemoteUSD 50k – 90k6d ago
Apply for this role

Opens LiteLLM's application page

Role

What you'll do.

Forward Deployed Engineer at LiteLLM, the world's leading open-source AI Gateway trusted by Adobe, Netflix, and NASA. This technical support role focuses on owning the customer support queue, diagnosing root-cause issues in LLM integrations, and driving customer success through hands-on troubleshooting and bug fixes. The ideal candidate combines deep technical expertise in AI systems, API integrations, and cloud infrastructure with a customer-obsessed mentality and strong problem-solving orientation.

Responsibilities

  • Own Support Queue and Ticket Management: Manage and prioritize the customer support queue, working through tickets systematically to resolve issues and drive customer success with the LiteLLM platform. Handle high volume of tickets while maintaining quality and thoroughness in each resolution.
  • Root Cause Analysis and Diagnosis: Diagnose complex customer issues by understanding the underlying technical problems rather than applying surface-level fixes. Analyze error logs, configuration issues, and integration problems to identify and address root causes in LLM gateway implementations.
  • Environment-Specific Issue Reproduction: Reproduce customer issues within their specific environments and configurations, including various cloud providers, deployment architectures, and LLM provider integrations. Set up test environments that mirror customer scenarios to validate issues and solutions.
  • Code Contribution and Bug Fixes: Submit pull requests for bug fixes, improvements, and enhancements to the LiteLLM codebase based on customer issues discovered. Contribute to the open-source project to improve platform reliability and user experience across the developer community.
  • Customer Advocacy and Internal Communication: Act as the technical voice of customers within the organization, communicating feature requests, pain points, and product feedback to the engineering and product teams. Provide detailed context and customer impact assessments to inform product development priorities.
  • Documentation and Knowledge Sharing: Create and maintain technical documentation, troubleshooting guides, and best practices for common issues. Share knowledge with the team to improve support efficiency and help customers self-serve through comprehensive resources.

Qualifications

What we look for.

Technical

  • LiteLLM Platform Expertise

    Deep familiarity with the LiteLLM AI Gateway surface, including routing, rate limiting, caching, cost management, and multi-provider LLM orchestration capabilities. Understanding of how the platform handles model switching, fallback mechanisms, and request optimization.

  • API Integration and Debugging

    Strong experience diagnosing API integration issues, including authentication, request/response handling, rate limiting, and error codes across multiple LLM providers such as OpenAI, Claude, Cohere, and others.

  • Large Language Model Understanding

    Solid foundational knowledge of how LLMs work, including model behavior, token limits, context windows, prompt engineering considerations, and differences between various model architectures and providers.

  • Cloud Infrastructure and Deployment

    Experience with cloud platforms (AWS, GCP, Azure), containerization (Docker, Kubernetes), and deployment architectures. Ability to troubleshoot issues related to networking, environment variables, secrets management, and container orchestration.

  • Debugging and Troubleshooting Tools

    Proficiency with debugging tools, log analysis, network inspection utilities, and system monitoring platforms. Ability to trace requests through distributed systems and identify bottlenecks or failures.

  • Python Programming

    Working knowledge of Python, as LiteLLM is built with Python and customers often integrate it into Python-based applications. Ability to read, understand, and potentially contribute to Python codebases.

Education

  • Bachelor's Degree in Computer Science or Related Field

    Formal education in computer science, software engineering, electrical engineering, or related technical discipline. Equivalent professional experience demonstrating deep technical foundation may be considered.

Experience

  • Technical Support or DevOps Experience

    3+ years of technical support, developer relations, customer success engineering, or DevOps experience. Proven track record of solving complex technical problems, diagnosing infrastructure issues, and working effectively with engineering teams.

  • API and Integration Support

    Demonstrated experience supporting customers with API integrations, SDKs, or platform implementations. Comfort working across multiple programming languages, frameworks, and deployment environments.

  • Open Source Community Engagement

    Familiarity with open-source development workflows, GitHub collaboration, and contributing to OSS projects. Understanding of how to engage with developer communities and gather feedback.

  • Problem-Solving Orientation

    Proven ability to tackle ambiguous problems independently, think analytically, and drive toward root-cause solutions. Experience with metrics-driven approaches to prioritization and impact measurement.

Skills

Required

  • Technical Problem Solving

    Exceptional ability to diagnose complex technical issues, understand system behavior under various conditions, and think through problems methodically to identify root causes rather than applying quick fixes.

  • API Integration Knowledge

    Deep understanding of RESTful APIs, authentication mechanisms, error handling, rate limiting, and integration patterns. Experience troubleshooting integration issues across multiple services and providers.

  • Python

    Working proficiency in Python programming, enabling code review, bug reproduction, and potential contribution to the LiteLLM codebase for customers and internal use cases.

  • Customer Communication

    Excellent written and verbal communication skills, translating complex technical concepts into clear explanations. Ability to communicate effectively across different technical levels and gather detailed information from customers.

  • Linux and Command Line

    Proficiency with Linux environments, shell scripting, and command-line tools essential for debugging, log analysis, and system troubleshooting in customer environments.

  • Log Analysis and Debugging

    Skilled at reading and interpreting logs, using debugging tools, and tracing system behavior to understand failures and performance issues in distributed systems.

Preferred

  • Kubernetes Experience

    Nice to have

    Experience deploying and troubleshooting applications in Kubernetes environments, including understanding of networking, storage, config management, and common failure scenarios.

  • LLM Provider Experience

    Nice to have

    Prior experience integrating with or troubleshooting issues with popular LLM providers including OpenAI, Anthropic Claude, Cohere, HuggingFace, or other major model providers.

  • Observability Tools

    Nice to have

    Experience with observability and monitoring tools such as Datadog, New Relic, Prometheus, or ELK stack for analyzing application performance and diagnosing production issues.

  • Git and Version Control

    Nice to have

    Proficiency with Git and GitHub workflows, including ability to understand pull requests, review code changes, and contribute patches to open-source projects.

  • Go or Rust

    Nice to have

    Familiarity with compiled languages like Go or Rust, beneficial for understanding performance-critical components and contributing to infrastructure improvements.

  • Developer Relations Background

    Nice to have

    Previous experience in developer relations, technical evangelism, or community engagement roles that required building relationships with technical audiences and advocating for customer needs.

Tech stack

Languages

PythonJavaScript/TypeScriptGoBash

Frameworks

FastAPIFlaskExpress.js

Databases

PostgreSQLRedisMongoDB

Tools

DockerKubernetesGitHubPostmanAWS / GCP / AzureGit

Other

LLM Provider APIsREST API PrinciplesDistributed Systems ConceptsObservability and Monitoring

Compensation

Pay and benefits.

Base·USD 50,000 – 90,000

Equity·Stock options

Benefits

  • Health Insurance

    Comprehensive health insurance coverage for employees, supporting preventive care and medical treatment needs.

  • Dental and Vision Coverage

    Dental and vision insurance benefits included as part of the comprehensive health plan, supporting overall wellness and healthcare access.

  • 401(k) Retirement Plan with Matching

    Competitive 401(k) retirement savings plan with 3.5% employer match, helping employees build long-term financial security.

  • Fast-Paced Growth Environment

    Opportunity to work in a rapidly growing technology company working with leading enterprises including Adobe, Netflix, and NASA, providing exposure to scaling challenges and innovation.

  • Deep Technical Ownership

    Meaningful technical autonomy and ownership of the support function, enabling personal growth through tackling complex problems and making strategic contributions to product improvement.

  • Open Source Impact

    Opportunity to contribute to and shape the world's most popular open-source AI Gateway, making direct impact on the developer community and broader AI infrastructure ecosystem.

  • Equity Compensation

    Stock options as part of competitive compensation package, aligning personal success with company growth and providing long-term financial upside potential.

Process

Interview steps.

  1. 01

    Initial Screening Call

    Preliminary conversation with the recruiting team to assess background, motivation for the role, and cultural fit. Typical duration 30 minutes covering career trajectory and interest in forward deployment engineering.

  2. 02

    Technical Assessment

    Evaluation of technical knowledge through discussion of past support experiences, problem-solving approach, and familiarity with APIs, cloud infrastructure, and LLM concepts. May include practical scenarios of customer issues.

  3. 03

    Product Deep Dive

    Hands-on exploration of the LiteLLM platform, discussing gateway architecture, routing mechanisms, multi-provider orchestration, and how customers typically integrate the product. Assessment of ability to quickly understand complex systems.

  4. 04

    Customer Interaction Simulation

    Role-play or case study exercise simulating real customer support scenarios. Evaluation of communication skills, customer empathy, problem-solving methodology, and ability to diagnose complex issues effectively.

  5. 05

    Team Interview

    Conversations with members of the support and engineering team to assess collaboration style, technical communication, and cultural alignment. Discussion of team processes and how the role fits within the organization.

  6. 06

    Final Offer Discussion

    Conversation with hiring manager or leadership to discuss compensation, benefits, expectations, and answer final questions about the role, team dynamics, and company vision.

Full posting

Original listing.

LiteLLM is the world's most popular AI Gateway, trusted by top companies like Adobe, Netflix, and NASA. Our platform empowers developers by providing secure, reliable access to LLMs and adjacent services, and we're looking for an Engineering Manager to lead the team building the leading OSS AI gateway.

About the Role

We're looking for a Forward Deployed Engineer to own our support queue and drive our customers to success. Because LiteLLM is a developer tool, this person needs to be technical. You'll dig into our customers' issues, understand them deeply, and unblock them.

The core of this role is simple: work the queue, address tickets, and make our customers successful with the product. We're looking for someone who is obsessed with getting to the root cause of problems rather than applying surface-level fixes. The best people in this role understand the real depth of a problem before they solve it.

Responsibilities

  • Own the support queue and work through tickets to drive customers to success

  • Diagnose customer issues and solve for the root cause, not just the symptom

  • Reproduce customer issues in their specific environments

  • Submit pull requests for bug fixes and improvements where needed

  • Act as the technical voice of the customer back to engineering

What We're Looking For

  • Technical depth and real familiarity with the LiteLLM product surface

  • Obsessed with customers and making them successful with the product

  • Obsessed with solving root causes rather than patching over problems

  • Metrics-driven and hardworking, ready to move through a high volume of tickets

  • A strong bias toward understanding problems deeply

Why Join LiteLLM?

  • Fast-paced growth environment with deep technical ownership.

  • Competitive salary, health, dental, and vision benefits, 401k plan with 3.5% match.

Redirects to LiteLLM's application page.

Other roles

More at LiteLLM.

View all 7 roles