AI Agent Developer

Company Description

PedaSys is an EdTech start-up based in India that provides innovative educational solutions. We specialise in corporate training strategy, Learning & Development systems, Learning Outcome Management, and Digital Transformation in L&D. Our services are geared towards enhancing educational experiences through advanced pedagogic consultancy and technology-driven solutions.

Role Description

We 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 is not a research role - we have clear specifications. You'll be shipping production code that serves real learners pursuing regulated qualifications.

What You'll Build

Immediate 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:

Core Technical Stack (Must Have 5+ Years)

Primary Technologies:

●      Python - All agent logic, RAG implementation, API development

●      Vector Databases - Pinecone, Weaviate, Qdrant, or ChromaDB (operational production experience)

●      LLM Integration - Anthropic Claude API, prompt engineering, structured outputs

●      RAG Architecture - Retrieval Augmented Generation, semantic search, hybrid search

●      Embedding Models - OpenAI, Cohere, or Sentence Transformers (generation and vector operations)

Required Experience

You Must Have:

●      5+ years Python development in production environments

●      2+ years working with vector databases in production

●      2+ years building RAG-based systems or LLM applications

●      Proven experience with embedding generation and semantic search

●      Experience designing and implementing APIs for agent-based systems

●      Strong understanding of prompt engineering and LLM behaviour

How We Work

Development Approach:

●      Clear specifications with detailed architecture documents

●      ReACT pattern (Reasoning → Action → Critique) for all agents

●      Work packages with defined deliverables and acceptance criteria

●      Parallel workstreams across the 4-person DS team

●      Regular integration testing between agents

Current 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 deployments

Technical Environment

Data Infrastructure:

●      5,000+ vectorised job descriptions across 23 sectors

●      NOS Database (vectorised)

●      OFQUAL Register (vectorised)

●      Career Pathways Database (500+ progression routes)

●      User Profile Database (operational)

Why This Role Matters

You'll be building AI that genuinely helps people progress in their careers. Not chatbots that hallucinate. Not marketing demos. Real production systems that:

●      Match learners to 5,000+ career roles with 95% accuracy

●      Map progression pathways with skill gap analysis

●      Deliver regulated qualifications (OFQUAL-compliant)

●      Provide formal assessments with human oversight

What We Offer

●      Competitive salary (based on experience)

●      Remote-first culture

●      Work with cutting-edge AI technology in production

●      Direct impact on people's career progression

●      Collaborative team that ships real products

●      Opportunity to work across the full agent architecture