V

Vichara

Asset management analytics and risk systems

AI Software Engineer

AI Application EngineeringConfirmed live in the last 24 hours
Full-timeBogotá, Bogota, ColombiaCOP1.2M - COP1.5M /yrHybrid

About the Job

Requirements

  • At least 5 years of experience as an AI or machine learning Engineer.
  • Experience with GPT-4o, PaLM 2, LangGraph, LangChain, Promptfoo, and SentenceTransformers.
  • Experience with retrieval-augmented generation frameworks including LanceDB, Pinecone, Elasticsearch, FAISS, and MongoDB.
  • Experience with LangGraph multi-agent orchestration, routing logic, and task decomposition.
  • Experience with BERT or domain-specific transformer fine-tuning and evaluation framework design.
  • Experience with FastAPI, Docker, Kubernetes (EKS or AKS), Redis Streams, and Azure DevOps continuous integration and continuous delivery.
  • Experience with OpenTelemetry, Signoz, and Prometheus.
  • Experience with Python, SQL, REST APIs, Git, Pandas, and NumPy.

Responsibilities

  • Architect, design, and lead multi-agent large language model systems using LangGraph, LangChain, and Promptfoo for prompt lifecycle management and benchmarking.
  • Build retrieval-augmented generation pipelines using hybrid dense and keyword vector search with LanceDB, Pinecone, or Elasticsearch.
  • Define system workflows for summarization, query routing, retrieval, and response generation to minimize latency and maximize precision.
  • Develop retrieval-augmented generation evaluation frameworks incorporating retrieval precision and recall, hallucination detection, and latency metrics aligned with analyst and business use cases.
  • Integrate GPT-4o, PaLM 2, and open-weight models such as LLaMA and Mistral for task-specific contextual question answering.
  • Fine-tune transformer models, including BERT and SentenceTransformers, for document classification, summarization, and sentiment analysis.
  • Manage prompt routing and variant testing using Promptfoo or equivalent tools.
  • Implement modular multi-agent architectures with task-specific agents for summarization, retrieval, classification, and reasoning.
  • Design fallback and recovery behaviors to support production robustness.
  • Use LangGraph for parallel and stateful agent orchestration, error recovery, and deterministic flow control.
  • Architect ingestion pipelines for structured and unstructured data, including financial statements, filings, and PDF documents.
  • Use MongoDB for metadata storage and Redis Streams for asynchronous task execution and caching.
  • Implement vector-based search and retrieval layers for high-throughput, low-latency AI systems.
  • Deploy end-to-end AI systems on AWS EKS or Azure Kubernetes Service, integrated with continuous integration and delivery pipelines using Azure DevOps.
  • Build monitoring dashboards using OpenTelemetry and Signoz to track latency, retrieval precision, and application health.
  • Enforce testing and regression validation using golden datasets and structured assertion checks for all large language model responses.
  • Collaborate with DevOps, MLOps, and application development teams to integrate AI APIs with React or FastAPI-based user interfaces.
  • Work with business analysts to translate credit, compliance, and customer-support requirements into actionable AI agent workflows.
  • Mentor a small team of generative AI developers and data engineers in retrieval-augmented generation, embeddings, and orchestration techniques.

Desired Qualifications

  • Knowledge of reranker-based retrieval using MiniLM or CrossEncoder.
  • Familiarity with prompt evaluation and scoring using BLEU, ROUGE, and Faithfulness.
  • Domain exposure to credit risk, banking, and investment analytics.
  • Experience with retrieval-augmented generation benchmark automation and model evaluation dashboards.

About the Company

Vichara

Asset management analytics and risk systems

Vichara provides software and services to asset managers, investment banks, and wealth managers to value assets, manage risk, and run complex portfolios. Its Solutions help with portfolio management, risk, and operations, while its Technology Services assist firms to design, build, integrate, and optimize their systems. The company combines domain-focused software with technology services to tailor end-to-end workflows for asset classes such as corporate credit, structured products, and real estate. Its goal is to help clients value assets accurately, control risk, and operate large, multi‑asset portfolios efficiently.

Company size
201-500
Company stage
Not listed
Total funding
Not listed
Headquarters
New York City, New York
Founded
2001

Recently Posted Jobs

Explore more opportunities at Vichara

See more jobs