AI Agent Developer

Location: Remote (with Bangalore Data Science team) Experience Required: 5+ years Contract Type: Full-timeSalary - ₹18-28 LPA dependent on experienceAbout ZavmoZavmo, your lifelong learning companion, is an AI-powered learning platform transforming professional development through intelligent personalisation. We've built an 18-agent multi-agent system that delivers the 4D Process (Discover, Discuss, Deliver, Demonstrate), integrating National Occupational Standards, OFQUAL frameworks, and career progression intelligence.Recently recognised as Top 20 AI Innovation Learning Tools by Training Magazine (2025).The RoleWe need an experienced AI engineer who can build and enhance specialised agents within our production multi-agent architecture. You'll be working with a 4-person Data Science team in Bangalore, implementing RAG-based agents that handle everything from role matching and career progression to assessment and quality assurance.This isn't a research role - we have clear specifications. You'll be shipping production code that serves real learners pursuing regulated qualifications.What You'll BuildImmediate Projects:Agent #3: Career Progression Intelligence Agent (RAG + pathway ranking algorithms)Agent #16: Learning Specification Triangulation Agent (LO/LO/AC alignment validation)Agent #17: Assessor Agent (formative/summative assessment with PASS/REFER/FAIL logic)Agent #18: Quality Assurance Agent (meta-agent for self-critique across all agents)Enhancement Work:Expand Agent #1 (Role Matching) to handle 5,000+ job descriptions across 23 sectorsEnhance Agent #8 (Content Recommendation) with job description contextualisationIntegrate Agent #10 (Conversational Facilitator) with role-specific examplesCore Technical Stack (Must Have 5+ Years)Primary Technologies:Python - All agent logic, RAG implementation, API developmentVector Databases - Pinecone, Weaviate, Qdrant, or ChromaDB (operational production experience)LLM Integration - Anthropic Claude API, prompt engineering, structured outputsRAG Architecture - Retrieval Augmented Generation, semantic search, hybrid searchEmbedding Models - OpenAI, Cohere, or Sentence Transformers (generation and vector operations)Essential Skills:API design and RESTful servicesJSON/data structure designDatabase schema design and migrationsIntegration testing and validationError handling and system reliabilityRequired ExperienceYou Must Have:5+ years Python development in production environments2+ years working with vector databases in production2+ years building RAG-based systems or LLM applicationsProven experience with embedding generation and semantic searchExperience designing and implementing APIs for agent-based systemsStrong understanding of prompt engineering and LLM behaviourIdeally You Also Have:Experience with multi-agent systems or agent orchestrationBackground in ML classification (scikit-learn, PyTorch)Knowledge of hybrid search algorithms (vector + keyword)Experience with xAPI or learning analytics standardsUnderstanding of UK education frameworks (NOS, OFQUAL) - nice to haveHR/L&D domain knowledge - nice to haveWhat We're Not Looking ForThis role isn't suitable if you:Need extensive training on Python, vectors, or RAG fundamentalsHaven't worked with production LLM applications beforeDon't have hands-on vector database experiencePrimarily work in research rather than production systemsNeed close supervision to implement clearly specified featuresThe TeamYou'll work with:4 Data Scientists in Bangalore - Your immediate team (DS1-DS4 structure)Juliette Denny - Founder, architect of the 4D Process and agent specificationsCosmo (CTO) - ADHD brain like a solar system, technical architecture leadGerard (Chairman) - Strategic oversightHow We WorkDevelopment Approach:Clear specifications with detailed architecture documentsReACT pattern (Reasoning → Action → Critique) for all agentsWork packages with defined deliverables and acceptance criteriaParallel workstreams across the 4-person DS teamRegular integration testing between agentsCurrent Sprint Example:B1: Agent #3 Core Logic (DS3, 7 days)B2: Integration Layer + Agent #16, #18 (DS4, 5 days)B3: Enhanced Agent #1 (DS3, 3 days)B4: Enhanced Agent #8 + #10 (DS4, 3 days)Timeline: 3-4 week sprints, production deploymentsTechnical EnvironmentData Infrastructure:5,000+ vectorised job descriptions across 23 sectorsNOS Database (vectorised)OFQUAL Register (vectorised)Career Pathways Database (500+ progression routes)User Profile Database (operational)Performance Requirements:Response times