Technical Lead, AI Initiatives

This is a fully remote position, open to applicants in India.

📋 Description

• Create and implement multi-agent systems, focusing on agent orchestration, delegation, and interaction patterns among tools.

• Develop scalable Retrieval-Augmented Generation (RAG) architectures utilizing vector databases, embedding pipelines, and data chunking techniques.

• Integrate and enhance Model Context Protocol (MCP) tools to ensure effective model-tool communication and automate workflows.

• Spearhead the development of AI-driven features, prototypes, and production solutions leveraging LLM APIs or self-hosted models.

• Design and optimize prompt engineering, prompt chains, agent loops, and refinement pipelines.

• Implement and oversee agent evaluation frameworks, including agent evaluations, scenario tests, and regression testing.

• Create automated evaluation harnesses to assess LLM quality, reliability, hallucination control, and performance metrics.

• Promote continuous improvements through A/B testing, reward models, and feedback mechanisms.

• Track system performance, latency, costs, and reliability, while executing optimization strategies.

• Mentor and lead engineers involved in AI, data, and backend development.

• Collaborate with product managers, researchers, and cross-functional teams to synchronize technological strategies with business goals.

• Conduct code reviews, uphold best practices, and ensure adherence to architectural standards.

• Manage technical roadmaps, sprint planning, and the execution of engineering tasks.

• Utilize cloud platforms (AWS/GCP/Azure) to deploy scalable AI services.

• Integrate vector databases such as Pinecone, Weaviate, Elasticsearch, among others.

• Develop APIs and microservices to provide AI capabilities to both internal and external stakeholders.

• Maintain secure, compliant, and efficient data pipelines for data ingestion and retrieval.

⛳️ Requirements

• Bachelor’s or Master’s degree in Computer Science, Engineering, AI, or a related discipline.

• Over 8 years of software engineering experience with a strong emphasis on backend architecture.

• At least 3 years of in-depth experience with LLMs, GPT models, agents, or advanced machine learning systems.

• Significant hands-on expertise with:

• - MCP tools and integration of LLM tools

• - Agent frameworks (e.g., OpenAI Agents, LangChain, LlamaIndex, custom agents)

• - RAG pipelines, embedding models, and vector stores

• - Agent evaluation methods, reliability testing, and model refinements

• Proficient in Python, TypeScript/Node.js, or comparable programming languages.

• Experience in deploying LLM applications and APIs in live environments.

• Comprehensive understanding of AI limitations, hallucination control, and safety protocols.

🏝️ Benefits

• Flexible working arrangements

• Professional development opportunities

• Competitive salary