Gen AI Lead Engineer (W2 Only)

Location: Remote, US

Mode: Contract

Core Responsibilities

• Collaborate with product, engineering, security, and business stakeholders.

• Drive adoption of AI across engineering teams.

• Establish governance, security, and responsible AI practices.

• Influence senior leadership through data-driven insights.

• Prior experience leading teams and large-scale engineering initiatives.

• Manage delivery plans, roadmaps, and stakeholder communication.

• Design, develop, and deploy production-grade AI Agents and multi-agent systems.

• Build and maintain complex workflows using LangGraph.

• Develop and integrate MCP (Model Context Protocol) servers/clients and A2A (Agent-to-Agent) communication.

• Build scalable, distributed AI systems with a focus on performance, reliability, and fault tolerance.

• Develop RAG pipelines, context engineering strategies, and prompt engineering best practices.

• Implement AI evaluation frameworks (quality, hallucination, regression, latency, etc.).

Must Have

• 8+ years of software engineering experience with 3+ years in Generative AI/LLM applications.

• 3+ years of experience with leading teams and large-scale engineering initiatives.

• Strong Java and Python development experience (Mandatory).

• Hands-on experience with LangChain and LangGraph.

• Experience building AI Agents and multi-agent workflows.

• Experience with Kubernetes and Azure cloud services.

• Experience with Azure OpenAI (or OpenAI APIs).

• Strong understanding of Prompt Engineering and Context Engineering.

• Experience implementing RAG pipelines.

• Experience with one or more Vector Databases: Pinecone, Weaviate, FAISS, or OpenSearch.

• Experience with MCP (Model Context Protocol) and/or A2A integrations.

• Knowledge of AI evaluation techniques and frameworks.

• Understanding of distributed systems, scalability, caching, retries, and asynchronous programming.

• Experience with Git, Docker, and GitHub Actions/CI-CD.

Nice to Have

• Experience with Node.js (Optional).

• Experience with FastMCP, FastAPI, Pydantic, Angular.

• Knowledge of GraphRAG and Knowledge Graphs.

• Experience with Semantic Kernel, LlamaIndex, CrewAI, or AutoGen.

• Familiarity with Redis, Kafka, RabbitMQ, or event-driven architectures.

• Experience with AI benchmarking tools such as Ragas or DeepEval.

• Exposure to OpenSearch hybrid search and HNSW indexing.

• Experience mentoring engineers and leading technical design discussions.

• Familiarity with Harness or other deployment/release engineering tools.