GenAI Developer — Tech Lead

Job Description:

Responsibilities

• Design, develop, and deploy production-grade Generative AI solutions including LLM integrations, RAG pipelines, AI agents, and prompt engineering frameworks.

• Build and optimize applications using foundation models (OpenAI GPT-4/o, Anthropic Claude, Gemini, Mistral, Llama, etc.) via API or self-hosted deployment.

• Implement vector databases (Pinecone, Weaviate, Qdrant, pgvector) and embedding strategies for semantic search and retrieval.

• Develop and manage LangChain, LlamaIndex, or custom orchestration frameworks for multi-step AI workflows.

• Integrate AI capabilities with existing enterprise systems, APIs, and data pipelines.

• Ensure models are fine-tuned, evaluated, and monitored for accuracy, safety, latency, and cost.

• Tech Lead Responsibilities

• Lead end-to-end technical design and architecture of GenAI systems with a focus on scalability and maintainability.

• Define best practices, coding standards, and review processes for the GenAI engineering workstream.

• Mentor and guide junior/mid-level developers on GenAI concepts, tooling, and implementation.

• Collaborate with product, data science, and platform teams to translate business requirements into technical solutions.

• Conduct technical interviews and evaluate third-party AI tools and vendors as needed.

• Prepare and present technical proposals, architecture decision records (ADRs), and engineering roadmaps.

• MLOps & Infrastructure

• Design and implement CI/CD pipelines for AI model deployment on cloud platforms (AWS, GCP, Azure).

• Set up evaluation harnesses, A/B testing frameworks, and observability tooling (LangSmith, Helicone, Arize, etc.).

• Manage containerization and orchestration (Docker, Kubernetes) for AI microservices.

• Implement guardrails, rate limiting, cost tracking, and latency monitoring for LLM APIs.

Qualification & Experience

• Strong proficiency with OpenAI, Anthropic, Google, Mistral, or Cohere APIs LLM APIs:

• LangChain, LlamaIndex, Semantic Kernel, or equivalent orchestration tools Frameworks:

• Pinecone, Weaviate, Qdrant, Chroma, or pgvector Vector Databases:

• Python (primary); TypeScript/Node.js desirable Languages:

• At least one of AWS (Bedrock, SageMaker), GCP (Vertex AI), or Azure (OpenAI Service) Cloud:

• Docker, Kubernetes, GitHub Actions / GitLab CI, model serving (FastAPI, vLLM, Triton) MLOps:

• LangSmith, Helicone, Arize AI, Weights & Biases, or similar Observability:

• Experience with fine-tuning (LoRA, QLoRA, RLHF) on open-source models (Llama, Mistral, Phi)

• Knowledge of AI safety, responsible AI principles, and content moderation approaches

• Familiarity with multi-modal models (vision-language, audio-to-text)

• Experience with graph databases (Neo4j) and knowledge graph integration

• Prior Tech Lead or Staff Engineer experience in a product engineering environment