Verified school opportunity
Software EngineerEO-6BB63H
School Serv (India) Solutions Pvt Ltd
School Serv (India) Solutions Pvt Ltd — Opp to MIMS Crescenta, Main Road, Kannamangala Village, Bidarahalli Hobli, Whitefield, Bangalore, Karnataka, India, Bangalore, Karnataka
Bangalore, Karnataka, IndiaFull TimeAbove 1 yearPostgraduate / Master's Degree
Job description
JUNIOR AI ENGINEERJob Overview We are looking for a Junior AI Engineer to build and maintain AI-powered features across our HR tech platform. You will work alongside our Senior AI Engineer to implement LLM integrations, build evaluation pipelines, and support the development of RAG-based conversational tools, resume parsing, and automated content generation features.
Key Responsibilities & Duties
Implement and maintain LLM API integrations using OpenAI-compatible endpoints (vLLM) for features like generation, data enrichment, and summary generationBuild and maintain prompt templates, structured output parsers, and JSON response handling for production AI featuresDevelop unit tests and evaluation harnesses to validate AI output quality across different models and prompt variationsAssist in maintaining RAG pipeline components including embedding generation, vector search, and context assemblyMonitor production AI services, triage failures, and implement retry/fallback logic for inference timeouts and errorsSupport the integration of AI services with FastAPI routes and Celery background tasksDocument AI feature implementations, model configurations, and deployment proceduresRequired Qualifications & Skills
1-3 years of software engineering experience with exposure to AI/ML projectsProficiency in Python with understanding of async programming conceptsFamiliarity with LLM APIs (OpenAI, Anthropic, or open-source equivalents) and prompt engineeringBasic understanding of vector databases and embeddings (pgvector, HuggingFace models)Experience with REST API development (FastAPI, Flask, or Django)Familiarity with Docker and containerized development workflowsUnderstanding of JSON parsing, error handling, and data validation in PythonEagerness to learn LLM inference optimization, GPU deployment, and RAG architecture
Job ScopeYou will focus on implementing and maintaining AI feature integrations, writing tests, and supporting the senior engineer on infrastructure work. This is a growth role with a clear path to owning independent AI features as you gain experience with the platform and inference stack.
Key Responsibilities & Duties
Implement and maintain LLM API integrations using OpenAI-compatible endpoints (vLLM) for features like generation, data enrichment, and summary generationBuild and maintain prompt templates, structured output parsers, and JSON response handling for production AI featuresDevelop unit tests and evaluation harnesses to validate AI output quality across different models and prompt variationsAssist in maintaining RAG pipeline components including embedding generation, vector search, and context assemblyMonitor production AI services, triage failures, and implement retry/fallback logic for inference timeouts and errorsSupport the integration of AI services with FastAPI routes and Celery background tasksDocument AI feature implementations, model configurations, and deployment proceduresRequired Qualifications & Skills
1-3 years of software engineering experience with exposure to AI/ML projectsProficiency in Python with understanding of async programming conceptsFamiliarity with LLM APIs (OpenAI, Anthropic, or open-source equivalents) and prompt engineeringBasic understanding of vector databases and embeddings (pgvector, HuggingFace models)Experience with REST API development (FastAPI, Flask, or Django)Familiarity with Docker and containerized development workflowsUnderstanding of JSON parsing, error handling, and data validation in PythonEagerness to learn LLM inference optimization, GPU deployment, and RAG architecture
Job ScopeYou will focus on implementing and maintaining AI feature integrations, writing tests, and supporting the senior engineer on infrastructure work. This is a growth role with a clear path to owning independent AI features as you gain experience with the platform and inference stack.