LLM Integration, LangChain Engineer

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

📋 Description

• Create, develop, and execute orchestration layers that connect enterprise data assets with generative AI models.

• Design and build sophisticated LLM applications and orchestrations utilizing LangChain, LangGraph, LlamaIndex, or AutoGen.

• Construct production-ready Retrieval-Augmented Generation (RAG) architectures featuring dynamic context chunking, document parsing, semantic metadata tagging, and reranking pipelines.

• Develop multi-agent reasoning chains and workflows incorporating custom tool calling, memory caching, and guardrail validations.

• Expose and utilize programmatic endpoints while establishing high-throughput API integrations that link foundational LLMs with internal corporate databases and CRMs.

• Implement AI evaluation and prompt tracking structures using observability platforms such as LangSmith and Arize Phoenix.

• Monitor token utilization, model latency, and prompt generation drift.

• Establish secure middleware execution barriers, which include text sanitization, PII data masking, prompt injection protections, and toxicity filtering.

• Optimize model inference expenses and context window budgets.

• Design semantic caching frameworks such as GPTCache.

⛳️ Requirements

• 4 to 8 years of experience in core enterprise backend web engineering or data pipelines.

• Over 2 years of hands-on experience in building, integrating, and deploying applications driven by Large Language Models (LLMs).

• Required developer certification from a prominent AI or cloud platform, such as Google Cloud Certified Professional ML Engineer, AWS Certified Machine Learning - Specialty, or verified framework specialization credentials.

• Strong technical proficiency in Python or TypeScript.

• Experience with vector representations.

• Knowledge of prompt engineering foundational mechanics.

• Familiarity with asynchronous web frameworks like FastAPI.

• Proficient in SQL.

• In-depth understanding of transformer model designs.

• Comprehension of text embedding properties.

• Knowledge of agentic tool execution cycles.

• Understanding of API orchestration limitations.

• Previous experience fine-tuning open-source LLMs using QLoRA or LoRA frameworks is preferred.

• Familiarity with Docker, Kubernetes, and modern DevSecOps CI/CD delivery loops is preferred.

🏝️ Benefits

• Remote work arrangement.

• Contract employment.