Senior Agentic AI Engineer

Akoncagua AI; Lakeland (FL); On-site; USD 150,000 - 190,000; Full time

Job summary

Akoncagua AI is seeking a Senior Agentic AI Engineer to design, build, evaluate, and productionize advanced AI agents across LLMs and multi-agent systems. The role involves hands-on work, architecture reviews, and mentoring engineers in production AI practices.

The ideal candidate has 5+ years in AI/ML or software engineering, with strong Python/PyTorch skills and experience deploying production LLMs, agent orchestration, and multimodal pipelines.

Qualifications

• 5+ years of professional AI/ML or software engineering experience.
• MS/PhD or equivalent; interdisciplinary CS/CE plus Civil Engineering preferred.
• Strong Python, PyTorch, data structures, debugging, and systems design.
• Hands-on with production LLM and agentic AI systems.
• Deep knowledge of Transformers, prompting, RAG, embeddings, and multimodal AI.
• Experience designing workflows with planning, tool execution, memory, and human-in-the-loop.

Responsibilities

• Design and build production-grade LLM and Agentic AI systems.
• Develop coding agents, computer-use agents, multi-agent systems, and human-in-the-loop.
• Build agent architectures with planning, execution, state/memory management, validation, retries, and tool integration.
• Integrate AI agents with APIs, databases, CAD/GIS platforms, and enterprise apps.
• Build production-grade agent harnesses and evaluation infra for regression testing and gating.
• Lead technical design reviews and mentor junior engineers.

Skills

Python

PyTorch

LLMs

agentic AI

systems design

debugging

cloud infrastructure

Docker

Kubernetes

multimodal AI

API integration

Education

MS/PhD in CS/CE/AI

Tools

Lang Graph

AutoGen/AG2

Hugging Face Transformers

TRL

PostGIS

FastAPI

PostgreSQL

Vector databases

Job description

Akoncagua AI is building domain-specialized AI systems for technically demanding industries.

Our work spans large language models, multimodal AI, agentic systems, model adaptation, finetuning, synthetic data, evaluation, and production AI infrastructure.

We are seeking a Senior Agentic AI Engineer with 5+ years of experience to design, build,

evaluate, and productionize advanced AI agents. This is a hands-on role for an engineer who can

work across LLMs, agent architectures, model training, evaluation, software systems, and

production infrastructure while providing technical guidance to other engineers.

Candidates with interdisciplinary experience across Computer Science/Computer Engineering and

Civil Engineering, particularly geospatial, CAD, land-development, or engineering automation

systems, are especially well suited for this role.

Role Overview

This role sits at the intersection of Agentic AI, applied machine learning, production software

engineering, and intelligent engineering systems.

The ideal candidate has hands-on experience building production LLM and agentic systems

involving planning, reasoning, tool use, retrieval, structured outputs, multimodal understanding,

validation, feedback loops, and long-horizon execution.

You will work across the complete AI lifecycle—from architecture and experimentation through

agent orchestration, fine-tuning, evaluation harnesses, observability, optimization, and production

deployment.

You will also mentor engineers, review architecture and code, establish AI engineering standards,

and contribute to the technical direction of Akoncagua AI's products.

Responsibilities

• Design and build production-grade LLM and Agentic AI systems for planning, reasoning, tool use, long-horizon execution, and multimodal workflows.
• Develop coding agents, computer-use agents, multi-agent systems, and human-in-the-loop
• Build agent architectures involving planning, execution, state/memory management, structured tool calling, validation, retries, fallbacks, feedback loops, and deterministic tool integration.
• Integrate AI agents with APIs, databases, search systems, computational engines, enterprise applications, CAD/GIS platforms, and domain-specific software.
• Build production-grade agent harnesses and evaluation infrastructure for regression testing, trajectory evaluation, tool-call evaluation, model/prompt comparison, failure analysis, and release gating.
• Build RAG and knowledge systems using embeddings, vector/hybrid retrieval, reranking, metadata filtering, and grounded generation.
• Develop multimodal pipelines involving text, images, PDFs, scanned documents, technical drawings, maps, and structured data.
• Design and curate datasets for model training, fine-tuning, evaluation, retrieval, and
• Fine-tune and adapt models using SFT, PEFT/LoRA/QLoRA, distillation, preference optimization, and other post-training methods where appropriate.
• Build AI observability and tracing for prompts, models, tool calls, agent trajectories, failures, retries, latency, token usage, and cost.
• Optimize AI systems for quality, reliability, latency, inference cost, and scalability.
• Translate cutting-edge AI research into reliable production systems.
• Lead technical design and architecture reviews and mentor junior and mid-level engineers.

Required Qualifications

• 5+ years of professional experience in AI/ML engineering, software engineering, or a closely related field.
• MS, PhD, or equivalent industry experience in Computer Science, Computer Engineering, Artificial Intelligence, Machine Learning, Applied Mathematics, or a related technical discipline; an interdisciplinary background combining Computer Science/Computer Engineering and Civil Engineering is highly preferred.
• Strong proficiency in Python, PyTorch, algorithms, data structures, debugging, profiling, testing, and systems design.
• Hands-on experience building and deploying production LLM and agentic AI systems.
• Strong understanding of LLMs, Transformers, prompt/context engineering, structured generation, tool/function calling, RAG, embeddings, and multimodal AI.
• Hands-on experience with coding agents, computer-use agents, multi-agent systems, and
• Experience with Lang Graph, AutoGen/AG2, or equivalent custom agent orchestration infrastructure.
• Experience designing workflows involving planning, tool execution, state management, memory, retries, validation, feedback loops, and human-in-the-loop execution. trajectory/tool-call evaluations, tracing, observability, and production monitoring.
• Experience with model training/fine-tuning, dataset development, synthetic data, and
• Experience with RAG, vector databases, retrieval systems, and document-processing
• Strong production engineering experience with APIs, databases, Docker, cloud infrastructure, CI/CD, and scalable systems.
• Ability to read, evaluate, reproduce, and adapt techniques from current AI research.
• Ability to independently take ambiguous AI problems from experimentation through
• Strong communication and technical leadership skills, including mentoring engineers and conducting architecture/code reviews.
• Experience or demonstrated understanding spanning Computer Science/Computer Engineering and Civil Engineering workflows is strongly preferred for this role, particularly where software or AI interacts with engineering calculations, spatial data, design systems, or engineering applications.

Preferred Qualifications

• Publications at top-tier conferences such as NeurIPS, ICML, ICLR, CVPR, ICCV, ECCV, ACL, or EMNLP, or significant patents/open-source contributions.
• Experience with advanced post-training methods including SFT, LoRA/QLoRA, PEFT, DPO, RLHF/RLAIF concepts, continual pre-training, distillation, and synthetic-data training.
• Experience with Hugging Face Transformers, Datasets, Accelerate, PEFT, and TRL.
• Experience with inference optimization including KV-cache optimization, speculative decoding, quantization, batching, model routing, and latency/cost optimization.
• Strong LeetCode or competitive-programming background, particularly in graphs, geometry, optimization, search, dynamic programming, and data structures.
• Experience with cloud platforms, Kubernetes, distributed systems, FastAPI, PostgreSQL, PostGIS, and vector databases.
• Experience building AI systems for scientific, engineering, geospatial, or other technically CAD automation, engineering-software plugins, or AI agents capable of interacting with CAD/GIS/engineering applications.
• Experience translating civil-engineering workflows into deterministic algorithms, optimization systems, computational tools, or AI-agent capabilities.