Devang Srivastava
@devangsrivastava
Backend engineer building cloud-native Java microservices and LangChain GPT/RAG pipelines in Kubernetes.
What I'm looking for
I’ve built LangChain-based LLM pipelines at Infosys for summarization, metadata extraction, intelligent search, automated documentation, and data enrichment across microservices.
On the RAG side, I’ve developed production-grade systems with LangChain + Chroma, including embedding generation, context ranking, retrieval orchestration, and prompt templating for consistent outputs.
I also integrate GPT models into Python microservices for internal automation, report generation, and dynamic knowledge retrieval—and I containerize and deploy them with Docker and Kubernetes.
Beyond that, I modernize legacy workflows with async utilities for high-throughput ingestion and API fan-out, and I’ve improved API latency using Redis caching, indexing, pagination, connection pooling, and lazy-load patterns.
Experience
Work history, roles, and key accomplishments
Designed and deployed LangChain-based LLM pipelines for summarization, metadata extraction, and intelligent search. Reduced API latency from 2s to 182ms via Redis caching and optimization.
Performed data curation on a 300,000+ sample dataset for ML model fine-tuning. Gained experience with GPT-based LLMs, LangChain, Python, and Spring Boot.
Education
Degrees, certifications, and relevant coursework
United College of Engineering & Research
Bachelor of Technology, Computer Science
Grade: 7.6/10
Bachelor of Technology in Computer Science from United College of Engineering & Research with a CGPA of 7.6/10.
Availability
Location
Authorized to work in
Job categories
Skills
Interested in hiring Devang?
You can contact Devang and 90k+ other talented remote workers on Himalayas.
Message DevangGet matched with your dream remote job
Sign up now and join over 250,000+ remote workers who receive personalized job alerts, curated job matches, and more for free!
