PlayStation IT is looking to develop future AI middleware and agent platforms to design and deliver intelligent agents that operate across enterprise domains.
Requirements
Proficiency in Python or TypeScript (ideally both) with strong software-engineering fundamentals (testing, design patterns, observability, performance tuning).
Practical knowledge of ML/GenAI concepts: embeddings, vector search, prompt engineering, fine-tuning, and evaluation metrics.
Solid understanding of workflow orchestration frameworks for LLM/GenAI pipelines.
Hands-on experience with data-pipeline tooling and batch/stream ETL.
Solid understanding of cloud platforms (AWS preferred), containerization (Docker, Kubernetes), and infrastructure-as-code (Terraform, CDK).
LLM tooling: LangChain, LangGraph, LlamaIndex, Hugging Face Transformers, OpenAI or Anthropic APIs
Data stores: Postgres, DynamoDB, Redis, and vector databases such as Pinecone, Weaviate, FAISS
Responsibilities
Architect and Operate AI Middleware: Design, implement, and manage Model Context Protocol (MCP) servers, gateways, and API wrappers that securely expose enterprise systems, tools, and data for AI agent consumption.
Build and Govern Agentic Workflows: Deploy and extend agentic AI platforms (e.g., LangGraph, LangChain) to deliver resilient orchestration, enforcing governance, tracing, audit logs, and human-in-the-loop controls.
Develop Enterprise Data & Context Pipelines: Build scalable pipelines for parsing, cleaning, embedding, and storing structured and unstructured enterprise data (text, code, multimedia) to enable retrieval-augmented generation and domain-specific agent knowledge.
Productize and Optimize AI Services: Translate prototypes into production-grade microservices (Python/TypeScript, Kubernetes, CI/CD), optimizing for latency, throughput, resilience, and token/cost efficiency.
Ensure Security, Compliance, and Reliability: Engineer AI middleware and workflows that meet enterprise standards for safety, governance, compliance, and fault tolerance, with built-in monitoring, telemetry, and automated evaluation harnesses.
Lead, Collaborate, and Mentor: Partner multi-functionally with architects, platform teams, and product owners to deliver business-aligned AI solutions, while mentoring engineers and staying at the forefront of emerging LLM and middleware trends.
Other
More than 10 years in software engineering, with a minimum of 3 years involved in building ML-, data-, or LLM-centric systems.
Excellent communication skills and a proven ability to collaborate across teams in a fast-paced environment.
This is a hands-on senior engineering role that requires a strong bias for action, an agile attitude, and the ability to change directions quickly as the AI landscape evolves.
Observability: distributed tracing, metrics dashboards, cost monitoring for token-based services
