naman_411
AI engineer in India seeking remote contract B2B (USD/EUR) or full-time roles, focused on retrieval quality, RAG evaluation, and agent reliability.
Skills
Domains
Show original post
Naman Gupta | India | Remote only | Contract (B2B, USD/EUR) or full-time AI engineer focused on retrieval quality and agent reliability. I measure retrieval before changing it. - Built and evaluated a production document-AI retrieval pipeline and LangGraph workflows. - rag-eval-harness (open source): 20 CUAD contracts, 50 queries, 114 annotated spans, 7 retrieval configs. Clause-aware chunking kept 99.1% of answer spans intact vs 43.0% for fixed-width. Hybrid BM25 + dense with RRF scored best (MRR 0.70). The reranker did not help. 87 unit tests. - Merged PR in Lamatic/AgentKit: EvidenceFit, compares chunking strategies against labelled evidence spans and returns a SHIP/TUNE/BLOCK verdict. - MCPHub: MCP server testing and inspection across SSE, Streamable HTTP and stdio, with latency percentiles. For contracts: a 5-day fixed-scope retrieval baseline on your pipeline (labelled eval set, failure patterns, prioritized fixes, harness handed over). Stack: Python, TypeScript, LangGraph, FastAPI, Next.js, Qdrant, pgvector, Postgres, Docker. Proof: https://namangupta.dev/production-ai GitHub: https://github.com/namanxdev/rag-eval-harness Email: [email protected]
Top job matches
10Paramark
San Francisco
Paramark is hiring a senior Software Engineer (L4) to build marketing measurement and experimentation systems; hybrid in San Francisco or remote in the US, $199K–$249K plus equity.
Curai
Remote
Curai is hiring senior software engineers for full-time remote US roles across full-stack, agentic AI, and marketing platform work in healthcare AI.
Search Atlas
Remote
Search Atlas is hiring a remote Product Engineer (PM role) for an AI marketing platform, requiring a technical B2B SaaS PM with hands-on coding/QA skills and EST-hour availability.
Rinse
Remote
Rinse is hiring a full-time Software Engineer for a remote US/Canada role or in several major North American cities, with a $80k-$200k salary and focus on full-stack, Python/Django, and AI/automation experience.
City Detect
Tuscaloosa, AL
City Detect is hiring a full-time Full Stack Product Engineer to build map-heavy, design-focused geospatial products for municipal customers, remote in the US with a $110k–$159k salary plus equity.
OpenSanctions
Berlin
OpenSanctions is hiring a Product Engineer to own commercial product systems across Python, SQL, and React/Next.js, with remote freelance work and an option for employment.
PrairieLearn
Remote
PrairieLearn is hiring a full-time remote US-only Full-Stack Software Engineer to work across TypeScript, Postgres, React, AWS, and AI tooling.
Cardog
Toronto
Cardog is hiring for multiple full-time roles across data, design, business, and field engineering, with remote options for some positions and Toronto/Ontario-based roles for others.
Enveritas
Remote
Backend Software Engineer role at Enveritas, a remote worldwide nonprofit focused on sustainability data systems for coffee, cocoa, and tea supply chains.
Snout
Remote
Snout is hiring multiple full-time remote engineering and product roles, including a Founding Data Engineer, for a pet health/veterinary care platform.