Building Advance AI & Cloud Native Software Using The "Virtual Silicon Valley" Model. Let’s Talk AI, Cloud and Outcomes.

Senior Lead – AI Engineering, LangGraph, Haystack, RAG Systems

AI EngineerMachine Learning EngineerFull TimeRemoteTeam 51-200Since 2019H1B No SponsorCompany Site LinkedIn

Location

United States

Posted

130 days ago

Salary

Not specified

Bachelor Degree8 yrs expEnglishDockerKubernetesMicroservicesPandasPost GISPy SparkPython

Job Description

• Design and oversee RAG pipelines using LangGraph, Haystack, LangChain, and OpenAI APIs for NeIO applications • Manage a team of 3–5 AI engineers; perform code reviews, pair programming, and architecture reviews • Develop FastAPI-based microservices and vectorized retrieval layers (Qdrant, FAISS, Pinecone) • Tune embedding quality, latency, and retrieval precision across multi-tenant data lakes • Integrate structured and spatial data using PostGIS, QGIS, GeoPandas • Establish model observability, explainability metrics, and audit trails • Translate business workflows (e.g., LeaseOps, Recon) into AI automation pipelines with measurable ROI • Advocate for enterprise-grade, open-source-first design principles

Job Requirements

8–12 years of experience in AI engineering
Expertise in AI / NLP with Hugging Face Transformers, spaCy, Haystack, OpenAI APIs
Experience with RAG / Agents: LangGraph, LangChain, retrieval orchestration
Knowledge of vector databases: Qdrant, FAISS, Pinecone, or Weaviate
Backend engineering skills in FastAPI, RESTful API design, async Python
Data processing experience with Pandas, DuckDB, PySpark, and Airbyte (preferred)
Geospatial skills with QGIS, PostGIS, and GeoPandas (Bonus)
MLOps knowledge with MLflow, DVC, Docker, Kubernetes (Preferred)
Version control using Git, GitHub Actions, and CI/CD automation
Passionate about building AI systems that move from prototype to production
Strong in data modeling, ontology design, and prompt engineering
Collaborate effectively with agile, cross-functional teams