Performance Engineer
About Ascendion
Ascendion is a leader in AI-Native platform driven software engineering company that underwrites outcomes, helping businesses innovate faster, smarter, and with greater impact. We partner with Global 2000 clients across North America, UK, Europe, and APAC to solve complex challenges in data, experience design, software product engineering, and workforce transformation. Powered by expert engineers, thousands of AI agents, and our Engineering to the Power of AI™ (EngineeringAI) method, we deliver measurable outcomes that build trust, unlock value, and accelerate growth. Learn more at ascendion.com
Ascendion | Engineering to elevate life
We have a culture built on opportunity, inclusion, and a spirit of partnership. Come, change the world with us:
- Build the coolest tech for world's leading brands
- Solve complex problems — and learn new skills
- Experience the power of transforming digital engineering for Fortune 500 clients
- Master your craft with leading training programs and hands-on experience
Experience a community of change makers!
Join a culture of high-performing innovators with endless ideas and a passion for tech. Our culture is the fabric of our company, and it is what makes us unique and diverse. The way we share ideas, learning, experiences, successes, and joy allows everyone to be their best at Ascendion.
Role
Summary
This
role demands an experienced Agentic AI Developer to design, build, and deploy
autonomous AI agents capable of reasoning, planning, and executing complex,
multi-step workflows within a fast-paced, agile environment.
Responsibilities
Design, develop, and test autonomous AI agents and multi-agent systems to
solve complex business problems.
Write clean, scalable, and maintainable production-grade code using Python.
Deploy, manage, and scale AI architectures and agentic workflows securely on
Google Cloud Platform (GCP).
Integrate Large Language Models (LLMs) with external APIs, internal
databases, and enterprise software toolchains.
Build and optimize advanced Retrieval-Augmented Generation (RAG) pipelines
and manage vector databases.
Implement robust evaluation frameworks, strict grounding techniques, and
anti-hallucination guardrails to ensure enterprise-grade reliability.
Monitor agent performance, debug complex AI reasoning loops, and optimize
systems for latency and cost.
Collaborate closely with product managers, data engineers, and stakeholders
to translate business requirements into technical AI solutions.
Required
Skills
Bachelor's or Master's degree in Computer Science, Artificial Intelligence,
Software Engineering, or a related technical field.
Proven hands-on experience building and deploying generative AI applications
in a production environment ( 6 to 12 months)
Advanced proficiency in Python programming with 7 – 9 years of experience,
including asynchronous programming and API development.
Experience with GCP services, specifically Vertex AI, Cloud Run, Cloud
Functions, and BigQuery (or) similar cloud experience in AWS or Azure
Deep understanding of LLM capabilities, advanced prompt engineering, and
context window management.
Strong foundational knowledge of vector search technologies, embeddings, and
semantic search methodologies.
Good
to have Skills
Experience designing complex multi-agent architectures where AI models
collaborate to solve tasks.
Practical experience with Gen AI orchestration and agentic frameworks such as
LangChain, LlamaIndex, AutoGen, or CrewAI.
Background in implementing MLOps pipelines, CI/CD for machine learning, and
automated model evaluation.
Solid understanding of data security, privacy compliance, and AI governance
best practices.
Experience
with containerization technologies like Docker and Kubernetes.