Lead AI Engineer - LLM & RAG Solutions (Remote - India)

Job Title: Lead AI Engineer - LLM & RAG Solutions (Remote - India)

Location: Fully Remote (Anywhere in India)
Working Model: Offshore, requiring 3–4 hours of daily overlap with US Eastern Time business hours.
Engagement Duration: Contract role, 6 months initial term with high likelihood of extension based on performance and project needs.

We are seeking a highly skilled and delivery-focused Lead AI Engineer to architect, build, and operationalize production-grade Generative AI (GenAI) systems. This role centers on the practical implementation of Large Language Model (LLM) applications and Retrieval-Augmented Generation (RAG) pipelines at scale, leveraging major cloud-based GenAI platforms.

You will act as a senior individual contributor and technical owner, combining deep hands-on development with strong architectural design. Success in this role is defined by the ability to translate cutting-edge AI capabilities into robust, secure, and scalable solutions that deliver tangible business value.

We are targeting a senior professional with 6-8+ years of total experience, demonstrating a clear progression into AI/ML and deep specialization in Generative AI. The ideal profile includes:

• 5+ years in Software/Data Engineering, building scalable systems, APIs, and data pipelines.

• 3+ years in Applied AI/ML Engineering, with experience taking machine learning models from concept to production.

• 1.5-2+ years of intensive, hands-on focus on GenAI/LLM & RAG systems. This must be recent, project-based experience in building and optimizing production-ready LLM applications, not just theoretical exploration.

• Solution Development & Implementation:

  • Design, build, and optimize end-to-end LLM applications and multi-agent systems using frameworks like LangChain.

  • Architect, implement, and manage RAG solutions for production, including sophisticated chunking strategies, embedding models, vector retrieval, and response synthesis.

  • Develop and integrate with cloud AI services and LLM APIs to create cohesive application architectures.

  • Write clean, maintainable, and scalable code to deliver AI-powered microservices and APIs.

• System Performance & Optimization:

  • Continuously debug, profile, and enhance LLM/RAG pipelines to improve latency, accuracy, and cost-efficiency.

  • Implement and refine retrieval strategies, evaluating performance using metrics such as Precision@K, Recall@K, MRR, nDCG, Faithfulness, and Answer Relevance.

  • Apply advanced prompt engineering and agent orchestration techniques to improve system outputs.

• Production Operationalization:

  • Engineer AI services with production-ready considerations: comprehensive monitoring, logging, rate limiting, error handling, and reliability patterns.

  • Implement AI safety, security, and compliance controls, including input validation, PII redaction, hallucination mitigation, and audit logging.

  • Ensure solutions adhere to multi-layered security standards encompassing IAM, data isolation, and network policies.

• Technical Leadership & Collaboration:

  • Lead technical solutioning sessions and make pivotal architecture decisions, guiding the team through example and expertise.

  • Stay abreast of the rapidly evolving GenAI landscape, evaluating new models, frameworks, and platform features for potential adoption.

  • Collaborate effectively with cross-functional teams (product, data, infrastructure) across different time zones.

GenAI & LLM Engineering:

• Proven, hands-on experience building and shipping LLM-powered applications to production.

• Expertise in developing LLM agents and workflows using frameworks such as LangChain or LlamaIndex.

• Deep, practical experience with leading cloud-based LLM APIs (e.g., Google's Gemini Pro or similar models from major providers).

• Strong ability to troubleshoot complex LLM systems across the entire stack—from data preprocessing and retrieval to generation and evaluation.

RAG & Vector Search:

• Hands-on experience designing and scaling RAG architectures.

• Proficiency with vector databases (e.g., Pinecone, Weaviate, Chroma, FAISS) and a solid grasp of vector similarity search fundamentals.

• Experience in measuring and improving RAG performance using established evaluation methodologies.

Cloud & Multi-Cloud Platforms:

• Strong hands-on development experience with Google Cloud Platform (GCP), particularly AI/ML services (Vertex AI), serverless compute, cloud storage, and related managed services.

• Practical experience working in multi-cloud environments, with specific integration expertise using AWS services (e.g., Bedrock, SageMaker, Lambda) alongside GCP.

Programming & Software Engineering:

• Excellent proficiency in Python for AI/ML development. Additional strength in PySpark or Java is a significant advantage.

• Demonstrated experience in building scalable, API-driven services and a firm understanding of API design, performance tuning, and system reliability.

AI Safety & Compliance:

• Direct experience implementing technical guardrails for AI systems, including content safety filters, PII handling, output verification, and compliance with internal governance policies.

• Infrastructure-as-Code (IaC) proficiency using tools like Terraform for environment provisioning and management.

• Background in Data Engineering, Data Science, or Analytics, including knowledge of ETL/ELT processes and data warehousing concepts.

• Experience in systematic evaluation and benchmarking of emerging LLM models and vendors.

• Exposure to bias detection and mitigation techniques within AI model pipelines.

• Prior experience in maintaining and scaling large-scale, high-traffic production RAG systems.

• You take ownership from concept to deployment, delivering production-ready, robust AI systems, not just prototypes or proofs-of-concept.

• You provide substantial contributions to the team's technical strategy and architecture, influencing long-term direction.

• You solve complex technical challenges independently while effectively collaborating with distributed team members.

• You proactively adapt to the fast-paced evolution of GenAI tools and platforms, ensuring our solutions remain effective and state-of-the-art.

• You embody a delivery-first mindset, balancing innovative research and experimentation with the discipline required to ship reliable software.