Python Engineer with GenAI

TekPioneers; Jersey City (NJ); On-site; USD 180,000 - 240,000; Full time

Job summary

TekPioneers in Jersey City seeks a highly experienced Principal Engineer - GenAI to lead design and delivery of enterprise AI solutions. You will own architecture, guide teams, and partner with business units to translate needs into scalable GenAI applications.

This role requires hands-on coding, cloud-based AI platforms, multi‑tier architectures, and governance of GenAI and Agentic AI deployments using AWS services and modern frameworks.

Qualifications

• 8-12 years of proven software development & system maintenance experience.

Responsibilities

• Lead application development from concept to testing, delivering business-aligned software solutions.

Skills

Leadership

Architecture design

Independent work

Team guidance

Stakeholder communication

Tools

AWS Bedrock

AWS AgentCore

LLMs

Embeddings

OpenSearch

Elasticsearch

Snowflake

Vector databases

Agent frameworks (AWS Strands)

AutoGen

CrewAI

Python

FastAPI

Flask

Django

Django REST Framework

C#

.NET

Job description

We are seeking a highly experienced Principal Engineer - GenAI with proven experience in software development, system design, and enterprise AI implementation. The ideal candidate will have a strong background in N-tiered applications, multi-tier architecture, scalable system design, and solid experience in designing and deploying GenAI and Agentic AI applications using modern AI frameworks and AWS services.

Responsibilities

• Accountable for leading application development supporting business objectives while demonstrating independence across software development lifecycle phases from concept and design to testing.
• Lead new and existing applications along with enhancements to applications, platforms, and infrastructure.
• Perform hands‑on coding while designing and architecting secure, scalable, and high‑performing data processing, analytics, GenAI, and Agentic AI solutions.
• Lead the design, architecture, deployment, and governance of enterprise‑grade GenAI and Agentic AI applications that deliver measurable business value.
• Design and deploy scalable AI solutions using AWS Bedrock, AWS AgentCore, LLMs, embeddings, and enterprise AI services.
• Architect multi‑agent workflows and agent orchestration solutions using frameworks such as AWS Strands, AutoGen, CrewAI, or similar agentic frameworks.
• Guide the implementation of advanced RAG‑based solutions for enterprise knowledge retrieval, semantic search, hybrid search, contextual grounding, and business workflow automation.
• Establish evaluation and testing approaches for GenAI and Agentic AI applications to validate response quality, safety, reliability, relevance, hallucination risk, and agent performance.
• Serve as a liaison to internal customers, research groups, product teams, and business support areas to translate business needs into scalable AI solutions.
• Provide technical guidance to junior programmers and software engineers; guide design discussions, architecture reviews, and technical decision‑making.
• Troubleshoot and maintain mid‑level to complex applications, ensuring performance, reliability, security, and operational readiness.

Qualifications

• 8 -12 years of proven experience in software development and system maintenance.
• Strong experience in designing, architecting, and deploying GenAI and Agentic AI applications in enterprise environments.
• Experience leading the implementation of enterprise‑scale GenAI solutions, ensuring they are robust, secure, scalable, and performant.
• Solid experience with Agentic AI frameworks such as AWS Strands, AutoGen, CrewAI, or similar agent orchestration frameworks.
• Strong understanding of multi‑agent architectures, agent orchestration patterns, Agent‑to‑Agent (A2A) communication protocols, planning, reasoning, memory management, and tool integration strategies.
• Experience designing and deploying AI agent solutions using AWS AgentCore, AWS Bedrock, LLMs, embeddings, and enterprise AI services.
• Experience creating and integrating Model Context Protocol (MCP) servers, tools, and enterprise system integrations.
• Strong experience with advanced RAG architectures and retrieval techniques, including semantic search, hybrid search, contextual retrieval, vector databases, knowledge grounding, and enterprise AI search solutions.
• Experience with OpenSearch, Elasticsearch, Snowflake, embedding models, vector databases, and enterprise search platforms.
• Experience creating evaluation and testing frameworks for GenAI and Agentic AI applications, including automated evaluation, benchmarking, response quality assessment, hallucination detection, safety validation, and agent performance measurement.
• Advanced knowledge of Python and modern frameworks such as FastAPI, Flask, Django, or Django REST Framework.
• Experience working on all aspects of enterprise‑scale AI implementations, including architecture, design, security, infrastructure, and GenAIOps.
• Demonstrated experience with N‑tiered applications and multi‑tier architecture.
• Highly experienced in developing scalable systems using software engineering best practices and design patterns.
• Strong AWS cloud experience preferred.
• Experience with C#/.NET is an added advantage.
• Highly experienced at leading teams, interacting with business partners or customers, and guiding project direction.
• Excellent understanding of object‑oriented design concepts and software development processes and methodologies.
• Superior organisational skills with the ability to prioritise effectively and keep teams focused on key outcomes.
• Leadership capability to guide architecture, design, and technical discussions.
• Demonstrated ability to work independently with minimal supervision.
• Passion for software engineering, AI innovation, and emerging technologies.