Artificial Intelligence Engineer

Synergy Business Consulting, Inc.; México; Remoto; MXN 600.000 - 1.400.000; Tempo pieno

Descrizione del lavoro

Synergy Business Consulting, Inc. is hiring a Senior AI Engineer to design, build, and operate agentic systems that automate enterprise workflows using video and rich visual media. The role is fully remote from LATAM with overlaps to US time zones, and involves shipping production-grade AI end-to-end.

You will work on backend and AI systems first, with opportunities to influence the user-facing product, and you will own delivery from architecture to deployment.

Competenze

• 5+ years shipping production software in enterprise or consumer environments.
• 2+ years architecting and optimizing search and information retrieval at scale.
• 6-12 months hands-on experience building agentic products (tool-using, conversational, long-running, or planning agents).
• 1+ year evaluating AI systems for quality, reliability, and safety at scale.
• Strong grasp of ML and statistics fundamentals: sampling, significance, overfitting, precision/recall.
• Fluency with LLM controls beyond simple API calls: temperature, top-p, logprobs, confidence scoring, model selection.
• Experience with agent frameworks such as OpenAI Agents SDK, LangGraph, Google ADK, or SmolAgents.
• BS in CS, EE, or equivalent experience.
• Experience with video, rich media, or multimodal AI; knowledge of digital and broadcast production workflows.
• OpenSearch or Elasticsearch
• FFmpeg, OpenCV, or similar media-processing tools.
• AWS (5+ years) and Azure (1+ year); Docker and Kubernetes; CI/CD
• WebSockets and stateful design patterns; React or Angular
• Model adaptation with LoRA, PEFT, or similar
• Familiarity with the C4 model and Agile environments

Mansioni

• Build agentic harnesses from scratch: tool use, multi-step chaining, reasoning, streaming, skills, multimodal integration, RAG, sandboxing, and state management.
• Design and run production APIs and services (REST, streaming, async workflows), choosing between synchronous calls, queues, event-driven patterns, and background jobs based on latency, reliability, and UX.
• Orchestrate large-scale batch workflows powered by LLMs, VLMs, and open-source models.
• Build evaluation systems: datasets, offline regression evals, online monitoring, rubric scoring, AI-as-judge, and human-in-the-loop review.
• Architect search and retrieval across lexical and embedding-based methods, tuning for relevance, ranking, recall, precision, and latency.
• Make clear tradeoffs between quality, reliability, latency, cost, and explainability in systems where model behavior is non-deterministic

Conoscenze

Production software

Search & IR at scale

Agentic AI/ planning agents

Evaluation at scale

ML fundamentals

LLM controls (temperature, top-p, logp

Formazione

BS in CS, EE, or equivalent experience

Strumenti

OpenAI Agents SDK

LangGraph

Google ADK

SmolAgents

OpenSearch/Elasticsearch

FFmpeg

OpenCV

Docker

Kubernetes

Descrizione del lavoro

What if your agents didn’t just answer questions, but actually ran real production workflows for a major media organization?

We’re hiring a Senior AI Engineer to design, build, and operate agentic systems that automate meaningful enterprise work using video and rich visual media. This is not a prototype role. You’ll ship production-grade AI that real teams depend on, and you’ll own it end to end.

The role at a glance

• Contract, fully remote from LATAM
• US time-zone overlap
• Compensation: competitive, based on experience
• Hands‑on role: backend and AI systems first, with room to shape the user‑facing product

What you’ll do

• Build agentic harnesses from scratch: tool use, multi‑step chaining, reasoning, streaming, skills, multimodal integration, RAG, sandboxing, and state management
• Design and run production APIs and services (REST, streaming, async workflows), choosing between synchronous calls, queues, event‑driven patterns, and background jobs based on latency, reliability, and UX
• Orchestrate large‑scale batch workflows powered by LLMs, VLMs, and open‑source models
• Build evaluation systems: datasets, offline regression evals, online monitoring, rubric scoring, AI‑as‑judge, and human‑in‑the‑loop review
• Architect search and retrieval across lexical and embedding‑based methods, tuning for relevance, ranking, recall, precision, and latency
• Make clear tradeoffs between quality, reliability, latency, cost, and explainability in systems where model behavior is non‑deterministic

What you bring

• 5+ years shipping production software in enterprise or consumer environments, not just POCs
• 2+ years architecting and optimizing search and information retrieval systems at scale
• 6‑12 months of hands‑on experience building agentic products (tool‑using, conversational, long‑running, or planning agents)
• 1+ year evaluating AI systems for quality, reliability, and safety at scale
• Strong grasp of ML and statistics fundamentals: sampling, significance, overfitting, precision/recall
• Fluency with LLM controls beyond simple API calls: temperature, top‑p, logprobs, confidence scoring, model selection
• Experience with agent frameworks such as OpenAI Agents SDK, LangGraph, Google ADK, or SmolAgents
• BS in CS, EE, or equivalent experience
• Experience with video, rich media, or multimodal AI; knowledge of digital and broadcast production workflows
• OpenSearch or Elasticsearch
• FFmpeg, OpenCV, or similar media‑processing tools
• AWS (5+ years) and Azure (1+ year); Docker and Kubernetes; CI/CD
• WebSockets and stateful design patterns; React or Angular
• Model adaptation with LoRA, PEFT, or similar
• Familiarity with the C4 model and Agile environments

Why this role

• Real production impact: your agents automate workflows that matter
• Direct work on frontier problems: multimodal AI, agentic orchestration, evaluation at scale
• Full ownership across the stack, from architecture to user experience